This is the homepage of Ma, Yiyang (马逸扬). Nice to see you here.
About me
|
I'm a third-year Master Candidate at Spatial and Temporal Restoration, Understanding and Compression Team (STRUCT), Peking University, and supervised by Prof. Jiaying Liu. |
Education
Peking University
09/2018 - 07/2022
Bachelor major in Intelligence Science and Technology, EECS.
09/2022 - 07/2025 (hopefully)
Master Candidate major in Data Science (Computer Science and Technology), AAIS.
Experience
Microsoft Research Asia
01/2022 - 08/2022
Research Intern, Multimedia Search and Mining Group.
DeepSeek AI
06/2024 - 10/2024
AGI Research Intern, Multimodality Group.
Research
Accepted Papers
Conference Papers
[1] Yiyang Ma, Wenhan Yang, Jiaying Liu. "Correcting Diffusion-Based Perceptual Image Compression with Privileged End-to-End Decoder", in proceedings of International Conference on Machine Learning (ICML), Vienna, Austria, July 2024. [arXiv]
[2] Yiyang Ma, Huan Yang, Wenhan Yang, Jianlong Fu and Jiaying Liu. "Solving Diffusion ODEs with Optimal Boundary Conditions for Better Image Super-Resolution", in proceedings of International Conference on Learning Representations (ICLR), Vienna, Austria, May 2024. [arXiv]
[3] Yiyang Ma, Huan Yang, Bei Liu, Jianlong Fu and Jiaying Liu. "AI Illustrator: Translating Raw Descriptions into Images by Prompt-based Cross-Modal Generation", in proceedings of ACM International Conference on Multimedia (ACM MM), Lisbon, Portugal, Oct. 2022. (Oral) [arXiv]
[4] Haowei Kuang, Yiyang Ma, Wenhan Yang, Zongming Guo, Jiaying Liu. "Consistency Guided Diffusion Model with Neural Syntax for Perceptual Image Compression", accepted by ACM International Conference on Multimedia (ACM MM), Melbourne, Australia, Oct. 2024.
[5] Lehong Wu, Lilang Lin, Jiahang Zhang, Yiyang Ma and Jiaying Liu. "MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion", accepted by European Conference on Computer Vision (ECCV), Milan, Italy, Sep. 2024.
[6] Ludan Ruan, Yiyang Ma, Huan Yang, Huiguo He, Bei Liu, Nicholas Jing Yuan, Qin Jin, Jianlong Fu and Baining Guo. "MM-Diffusion: Learning Multi-modal Diffusion Models for Joint Audio and Video Generation", in proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, June 2023. [arXiv]
[7] Weiyu Zhang, Yiyang Ma, Di Zhu, Lei Dong and Yu Liu. "MetroGAN: Simulating Urban Morphology with Generative Adversarial Network", in proceedings of ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD), Washington D.C., U.S.A., Aug. 2022. [arXiv]
[8] Shixing Yu, Yiyang Ma, Wei Xiang, Wenhan Yang, and Jiaying Liu. "Meta-Interpolation: Time-Arbitrary Frame Interpolation via Dual Meta-Learning", in proceedings of IEEE International Symposium on Circuits and Systems (ISCAS), Austin, U.S.A., May 2022. (MSA-TC Best Paper) [arXiv]
Journal Papers
[1] Yiyang Ma*, Haowei Kuang*, Huan Yang, Jianlong Fu, and Jiaying Liu. "Prompt-Based Modality Bridging for Unified Text-to-Face Generation and Manipulation", accepted by ACM Transactions on Multimedia Computing Communications and Applications (ACM TOMM).
[2] Jialu Sui, Yiyang Ma, Wenhan Yang, Xiaokang Zhang, Man-On Pun, and Jiaying Liu. "Diffusion Enhancement for Cloud Removal in Ultra-Resolution Remote Sensing Imagery", accepted by IEEE Transactions on Geoscience and Remote Sensing (IEEE TGRS). [arXiv]
Preprints or Papers under Review
[1] Yiyang Ma, Xingchao Liu*, Xiaokang Chen*, Wen Liu*, Chengyue Wu, Zhiyu Wu, Zizheng Pan, Zhenda Xie, Haowei Zhang, Xingkai yu, Liang Zhao, Yisong Wang, Jiaying Liu and Chong Ruan. "JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation", arXiv preprint. [arXiv]
[2] Yiyang Ma, Huan Yang, Wenjing Wang, Jianlong Fu and Jiaying Liu. "Unified Multi-Modal Latent Diffusion for Joint Subject and Text Conditional Image Generation", arXiv preprint. [arXiv]
[3] Chengyue Wu, Xiaokang Chen, Zhiyu Wu, Yiyang Ma, Xingchao Liu, Zizheng Pan, Wen Liu, Zhenda Xie, Xingkai Yu, Chong Ruan and Ping Luo. "Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation", arXiv preprint. [arXiv]
*Equal Contribution
Others
Gold Medalist (or First Prize Winner officially) in the 34th Chinese Physics Olympiad (CPhO), Chongqing, Nov. 2017.
Bronze Medalist (or Third Prize Winner officially) in the 33th Chinese Physics Olympiad (CPhO), Wuhan and Huanggang, Nov. 2016.
I'm still loving physics even if I may not have any chance to learn it again. So sad.
Contact me
Please send e-mail to